© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 4020
    Prev
    Next
    INDEX
    Explanations

    edge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frente
    -0.09
     sacked
    -0.09
    ä»°
    -0.08
     triangle
    -0.08
     sands
    -0.08
     ExecutionContext
    -0.08
    à¹īวย
    -0.08
     roofs
    -0.08
     heights
    -0.08
     fronts
    -0.08
    POSITIVE LOGITS
     edges
    0.57
     edge
    0.56
    è¾¹
    0.45
     Edge
    0.42
    edges
    0.42
    edge
    0.42
    Edge
    0.41
     peripheral
    0.39
    éĤĬ
    0.39
    _edge
    0.37
    Activations Density 0.147%

    No Known Activations